Algorithm Can See Your Pulse Rate in Your Face

What's the Latest Development?

MIT medical researchers have created an algorithm that accurately measures a person's pulse by tracking how the head moves involuntarily when blood is pumped from the heart to the brain. The algorithm works using techniques already used by computer vision systems. "First, it uses standard face recognition to distinguish the subject’s head from the rest of the image. Then it randomly selects 500 to 1,000 distinct points, clustered around the subjects’ mouths and noses, whose movement it tracks from frame to frame. Next, it filters out any frame-to-frame movements whose temporal frequency falls outside the range of a normal heartbeat."

What's the Big Idea?

The novel way to measure human pulse rates is consistently accurate to within a few beats per minute of those produced by electrocardiograms (EKGs). "It was also able to provide useful estimates of the time intervals between beats, a measurement that can be used to identify patients at risk for cardiac events." John Guttag, who described the algorithm for MIT, believes it could detect arterial obstruction, which could cause the blood to flow unevenly to the head. "Can you use the same type of techniques to look for bilateral asymmetries?" he asked. "What would it mean if you had more motion on one side than the other?"

Photo credit: Shutterstock.com

Read it at MIT News

comments powered by Disqus